Feature extraction without learning in an analog spatial pooler memristive-CMOS circuit design of hierarchical temporal memory

Olga Krestinskaya, Alex Pappachen James

Research output: Contribution to journalArticlepeer-review

21 Scopus citations

Abstract

Hierarchical temporal memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This sparsity is introduced by the binary weights and random weight assignment in the initialization stage of the HTM. We propose the alternative deterministic method for the HTM initialization stage, which connects the HTM weights to the input data and preserves natural sparsity of the input information. Further, we introduce the hardware implementation of the deterministic approach and compare it to the traditional HTM and existing hardware implementation. We test the proposed approach on the face recognition problem and show that it outperforms the conventional HTM approach.
Original languageEnglish (US)
Pages (from-to)457-465
Number of pages9
JournalAnalog Integrated Circuits and Signal Processing
Volume95
Issue number3
DOIs
StatePublished - Jun 1 2018
Externally publishedYes

ASJC Scopus subject areas

  • Hardware and Architecture
  • Signal Processing
  • Surfaces, Coatings and Films

Fingerprint

Dive into the research topics of 'Feature extraction without learning in an analog spatial pooler memristive-CMOS circuit design of hierarchical temporal memory'. Together they form a unique fingerprint.

Cite this